CN111964909A - Rolling bearing operation state detection method, fault diagnosis method and system - Google Patents
Rolling bearing operation state detection method, fault diagnosis method and system Download PDFInfo
- Publication number
- CN111964909A CN111964909A CN202010858165.8A CN202010858165A CN111964909A CN 111964909 A CN111964909 A CN 111964909A CN 202010858165 A CN202010858165 A CN 202010858165A CN 111964909 A CN111964909 A CN 111964909A
- Authority
- CN
- China
- Prior art keywords
- rolling bearing
- short
- map
- fault
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention belongs to the technical field of state monitoring and fault diagnosis of mechanical systems, and provides a rolling bearing operation state detection method, a fault diagnosis method and a system. The rolling bearing running state detection method comprises the steps of extracting a short-time period map of a vibration signal of a rolling bearing; mapping the short-time period map by using the undirected weighted map to obtain a series of map frequencies; and monitoring the change trend of the main spectrum frequency to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing. The vibration signal obtained by monitoring is analyzed and processed, the running state of the rolling bearing is monitored, and the rolling bearing is timely and accurately monitored when an early fault occurs.
Description
Technical Field
The invention belongs to the technical field of state monitoring and fault diagnosis of mechanical systems, and particularly relates to a rolling bearing operation state detection method, a fault diagnosis method and a rolling bearing operation state detection system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The rolling bearing is widely applied to modern rotating machinery, the performance of the whole machine, such as precision, reliability, service life and the like, is often directly influenced by whether the running state of the rolling bearing is normal, and meanwhile, the rolling bearing is also one of the most common fault sources of the rotating machinery. The defects of the rolling bearing can cause abnormal vibration and noise of equipment, and further develop into faults, so that the equipment is damaged, and even disastrous accidents occur. Therefore, the rolling bearing can be effectively detected in an early state and diagnosed in a fault, and the rolling bearing detection method has important significance for reducing maintenance cost and ensuring reliability.
Conventional bearing fault detection and diagnosis is performed by analyzing status signals (e.g., vibration, temperature, sound, etc.) collected during operation of the bearing. Vibration-based methods have been extensively studied in this field, as vibration signals can provide the most essential information about bearing failure. The bearing may have different failure types during degradation, mainly due to defects on the inner and outer races and the balls. Different types of faults can result in unique frequency components. Therefore, conventional spectral analysis methods focus on monitoring these frequency components for health status identification. This method relies on parameters that extract frequency components associated with the fault. However, it is very difficult, if not impossible, to calculate these parameters in this method. In response to this drawback, some proposed methods extract useful information from the spectrum by using high-level features (such as histogram, image, spectral kurtosis, etc.). However, the inventors have found that these methods assume independence between frequencies, neglecting the correlation in which excavation is hidden, and thus fail to accurately detect early failure of the rolling bearing in time.
Disclosure of Invention
In order to solve the problems, the invention provides a rolling bearing running state detection method and system, which analyze and process the vibration signals obtained by monitoring, realize the running state monitoring of the rolling bearing and timely and accurately monitor the rolling bearing when an early fault occurs.
The invention provides a rolling bearing operating state fault diagnosis method and system, which are used for judging faults based on detected early faults of a rolling bearing so as to improve the maintenance efficiency of the rolling bearing.
The invention adopts the following technical scheme that:
a first aspect of the invention provides a rolling bearing operating condition detection method.
In one or more embodiments, a rolling bearing operation state detection method includes:
extracting a short-time period map of a vibration signal of the rolling bearing;
mapping the short-time period map by using the undirected weighted map to obtain a series of map frequencies;
and monitoring the change trend of the main spectrum frequency to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing.
A second aspect of the invention provides a rolling bearing operating condition detection system.
In one or more embodiments, a rolling bearing operation state detection system includes:
the short-time period map extraction module is used for extracting a short-time period map of a vibration signal of the rolling bearing;
the map frequency mapping module is used for mapping the short-time period map by utilizing the undirected weighted map to obtain a series of map frequencies;
and the main spectrum frequency monitoring module is used for monitoring the change trend of the main spectrum frequency so as to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing.
A third aspect of the invention provides a rolling bearing operating condition failure diagnosis method.
In one or more embodiments, a rolling bearing operation state fault diagnosis method includes:
judging that the rolling bearing has early failure by adopting the rolling bearing running state detection method;
and (4) sending the undirected weighted graph structure at the current fault moment into a K neighbor classifier to determine the fault type.
A fourth aspect of the invention provides an operational state fault diagnosis system for a rolling bearing.
In one or more embodiments, a rolling bearing operation state fault diagnosis system includes:
the early fault detection module is used for judging that the rolling bearing has early faults by adopting the rolling bearing running state detection method;
and the fault type identification module is used for sending the undirected weighted graph structure of the current fault moment into the K neighbor classifier and determining the fault type.
A fifth aspect of the invention provides a computer-readable storage medium.
In one or more embodiments, a computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, implements the steps in the rolling bearing operating state detection method as described above.
In one or more embodiments, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps in the rolling bearing health status failure diagnosis method as described above.
Compared with the prior art, the invention has the beneficial effects that:
(1) the graph modeling is applied to time-frequency analysis of rotary machine vibration signals, and the short-time period graph is constructed into the undirected weighted graph on the basis of considering data correlation among different frequency sampling points, so that a unified framework is provided for rolling bearing running state evaluation and fault diagnosis, and subsequent monitoring and diagnosis are more accurate and comprehensive.
(2) The method is used for evaluating the health state of the rotating machine based on the undirected weighted graph, and mapping the short-time period graph by using the undirected weighted graph to obtain a series of graph frequencies, wherein the short-time period graph has stronger analysis capability on non-stationary signals, and can identify early fault information with weak energy and short duration.
(3) The method diagnoses the fault types of the rotating machinery by using the K-nearest neighbor classifier based on the graph, and accurately identifies different fault types under the condition of only using a small number of training samples, so that the maintenance efficiency of the rolling bearing is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flowchart of a rolling bearing operating condition detection method according to an embodiment of the present invention;
fig. 2 is a flowchart of a rolling bearing operating state fault diagnosis method according to an embodiment of the present invention;
FIG. 3 is a graph of the original vibration signals of the rolling bearing used in the experiment of the present invention;
FIG. 4 is a graph showing the detection result of the rolling bearing fault based on the frequency of the main spectrum according to the embodiment of the present invention;
fig. 5 is a diagram illustrating an example of fault identification according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
Referring to fig. 1, the rolling bearing operating condition detection method of the present embodiment includes:
s101: and extracting a short-time period map of the vibration signal of the rolling bearing.
In step S101, the process of extracting the short-time period map of the vibration signal of the rolling bearing is:
extracting short-time Fourier transform of a vibration signal of the rolling bearing by adopting a Hanning window;
and obtaining a discrete short-time Fourier spectrum according to the short-time Fourier transform, and calculating a corresponding short-time period map.
For example: and collecting a vibration signal x (N) of the monitored bearing by using a vibration acceleration sensor, wherein N belongs to [0, N-1 ]. Fig. 3 shows a measured signal. And N is the number of sampling points of the time sequence signal. The short-time Fourier transform of x (n):
wherein, Δ t is the time interval of short-time Fourier transform, Δ f is the frequency interval, Y (K, M) is the output of the signal at time M Δ t, M is more than or equal to 0 and less than or equal to M and frequency K Δ f, K is more than or equal to 0 and less than or equal to K, and the () represents convolution operation. Omega is a window function, and can be selected according to the characteristics of the original signal and the requirements of frequency resolution and time resolution. This embodiment uses a short-time fourier transform of the hanning window raw signal.
From the short-time Fourier transform of the extracted original signal, a short-time period map can be directly calculated according to the following formula
S102: mapping the short-time period map by using the undirected weighted map to obtain a series of map frequencies.
The existing method is insufficient in consideration of the correlation among data, and the graph structure can integrally express a cluster of data on data modeling and simultaneously express the correlation among data samples.
The present embodiment constructs a space-time diagram by the following method:
regarding each frequency sampling point as a node of the graph model, and simultaneously connecting each pair of sampling points v (i) and v (j) to form a weighted edge Li，j(ii) a Then, each weighted edge is attached with a weight di，j(ii) a Finally, the created undirected weighting graph is expressed as an adjacency matrix α, i.e., α ═ di，j}. The weighted edges in the graph structure are used to characterize the correlation between nodes, as shown in the following equation:
wherein Cov (,) represents covariance, Dis (,) represents euclidean distance,
is a de-averaging operation.
Wherein e1The short-time period map comprises time information and frequency information. The above process is the process of modeling the space-time diagram of the vibration signal of the rolling bearing.
Extracting map frequency by feature vector
Mapping the short-time period map to obtain a series of map frequencies { C }1(m)}，...，{Cz(m)}，...，{Cn(m) } namely that the first and second,
due to the fact that
Is a vector of 1 x K, and,p (K, M) is a K M matrix, thus { Cz(M) is a 1 × M vector.
S103: and monitoring the change trend of the main spectrum frequency to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing.
Mapping short-time period maps using undirected weighted maps to obtain a range of map frequencies { C }1}，...，{Cz-according to the nature of the extracted map frequencies:
(a){Czthan { C }z+1The health state of the rotating machine can be reflected better.
(b) The rotating machine state information contained in all map frequencies is independent of each other.
(c) The operating state of the rotating machine can be reflected in the first s pattern frequencies { C }1(m)}，...，{Cs(m)}。
(d) These map frequency trends are smooth when the rotating machine is operating normally. When a fault occurs, a large fluctuation occurs.
And monitoring the main spectrum frequency { C1} by using a change point detection algorithm based on Gaussian distribution hypothesis to find early failure signs of the rolling bearing, thereby realizing early failure detection of the rolling bearing.
For main spectrum frequency { C1(m) } abnormal point inspection is performed to evaluate the operation state of the rolling bearing. Generally, an abnormal situation in the operation of a rotary machine can be found by performing a hypothesis test by setting a fixed threshold value. A certain control interval can be set according to the mean value and the variance of data distribution to monitor the abnormity in the running process of the rotating machine. And carrying out abnormal decision according to the hypothesis test (6).
Wherein A ═ muh-1-n*σh-1，μh-1+n*σh-1]To a confidence interval, μh-1And σh-1Respectively frequency of main spectrum observed
The resulting mean and variance are calculated. Fig. 4 shows the early failure detection result of the measured signal in fig. 3, and it can be seen that the method can detect the failure early and timely and give a corresponding indication.
In the embodiment, graph modeling is applied to time-frequency analysis of rotary machine vibration signals, and on the basis of considering data correlation among different frequency sampling points, a short-time period graph is constructed into an undirected weighted graph, so that a unified framework is provided for rolling bearing running state evaluation and fault diagnosis, and subsequent monitoring and diagnosis are more accurate and comprehensive.
The health state of the rotating machine is evaluated based on the undirected weighted graph, the undirected weighted graph is used for mapping the short-time period graph to obtain a series of graph frequencies, the short-time period graph has strong analysis capability on non-stationary signals, and early fault information with weak energy and short duration can be identified.
Example two
This example provides a rolling bearing running state detecting system, it includes:
(1) and the short-time period map extraction module is used for extracting a short-time period map of the vibration signal of the rolling bearing.
Specifically, the process of extracting the short-time period map of the vibration signal of the rolling bearing is as follows:
extracting short-time Fourier transform of a vibration signal of the rolling bearing by adopting a Hanning window;
and obtaining a discrete short-time Fourier spectrum according to the short-time Fourier transform, and calculating a corresponding short-time period map.
For example: and collecting a vibration signal x (N) of the monitored bearing by using a vibration acceleration sensor, wherein N belongs to [0, N-1 ]. Fig. 3 shows a measured signal. And N is the number of sampling points of the time sequence signal. The short-time Fourier transform of x (n):
wherein, Δ t is the time interval of short-time Fourier transform, Δ f is the frequency interval, Y (K, M) is the output of the signal at time M Δ t, M is more than or equal to 0 and less than or equal to M and frequency K Δ f, K is more than or equal to 0 and less than or equal to K, and the () represents convolution operation. Omega is a window function, and can be selected according to the characteristics of the original signal and the requirements of frequency resolution and time resolution. This embodiment uses a short-time fourier transform of the hanning window raw signal.
From the short-time Fourier transform of the extracted original signal, a short-time period map can be directly calculated according to the following formula
(2) And the map frequency mapping module is used for mapping the short-time period map by utilizing the undirected weighted map to obtain a series of map frequencies.
The existing method is insufficient in consideration of the correlation among data, and the graph structure can integrally express a cluster of data on data modeling and simultaneously express the correlation among data samples.
The present embodiment constructs a space-time diagram by the following method:
regarding each frequency sampling point as a node of the graph model, and simultaneously connecting each pair of sampling points v (i) and v (j) to form a weighted edge Li，j(ii) a Then, each weighted edge is attached with a weight di，j(ii) a Finally, the created undirected weighting graph is expressed as an adjacency matrix α, i.e., α ═ di，j}. The weighted edges in the graph structure are used to characterize the correlation between nodes, as shown in the following equation:
wherein Cov (,) represents covariance, Dis (,) represents euclidean distance,
is a de-averaging operation.
Wherein e1The short-time period map comprises time information and frequency information. The above process is the process of modeling the space-time diagram of the vibration signal of the rolling bearing.
Extracting map frequency by feature vector
Mapping the short-time period map to obtain a series of map frequencies { C }1(m)}，...，{Cz(m)}，...，{Cn(m) } namely that the first and second,
due to the fact that
Is a vector of 1 XK, P (K, M) is a matrix of K XM, so { Cz(M) is a 1 × M vector.
(3) And the main spectrum frequency monitoring module is used for monitoring the change trend of the main spectrum frequency so as to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing.
Using undirected weighted graph for short epochThe phase map is mapped to obtain a series of map frequencies { C }1}，...，{Cz-according to the nature of the extracted map frequencies:
(a){Czthan { C }z+1The health state of the rotating machine can be reflected better.
(b) The rotating machine state information contained in all map frequencies is independent of each other.
(c) The operating state of the rotating machine can be reflected in the first s pattern frequencies { C }1(m)}，...，{Cs(m)}。
(d) These map frequency trends are smooth when the rotating machine is operating normally. When a fault occurs, a large fluctuation occurs.
And monitoring the main spectrum frequency { C1} by using a change point detection algorithm based on Gaussian distribution hypothesis to find early failure signs of the rolling bearing, thereby realizing early failure detection of the rolling bearing.
For main spectrum frequency { C1(m) } abnormal point inspection is performed to evaluate the operation state of the rolling bearing. Generally, an abnormal situation in the operation of a rotary machine can be found by performing a hypothesis test by setting a fixed threshold value. A certain control interval can be set according to the mean value and the variance of data distribution to monitor the abnormity in the running process of the rotating machine. And carrying out abnormal decision according to the hypothesis test (6).
Wherein A ═ muh-1-n*σh-1，μh-1+n*σh-1]To a confidence interval, μh-1And σh-1Respectively frequency of main spectrum observed
The resulting mean and variance are calculated. Fig. 4 shows the early failure detection result of the measured signal in fig. 3, and it can be seen that the method can detect the failure early and timely and give a corresponding indication.
In the embodiment, graph modeling is applied to time-frequency analysis of rotary machine vibration signals, and on the basis of considering data correlation among different frequency sampling points, a short-time period graph is constructed into an undirected weighted graph, so that a unified framework is provided for rolling bearing running state evaluation and fault diagnosis, and subsequent monitoring and diagnosis are more accurate and comprehensive.
The health state of the rotating machine is evaluated based on the undirected weighted graph, the undirected weighted graph is used for mapping the short-time period graph to obtain a series of graph frequencies, the short-time period graph has strong analysis capability on non-stationary signals, and early fault information with weak energy and short duration can be identified.
EXAMPLE III
As shown in fig. 2, the present embodiment provides a rolling bearing operating condition fault diagnosis method, including:
step 1: by adopting the rolling bearing running state detection method according to the first embodiment, the early failure of the rolling bearing is judged.
The rolling bearing operation state detection method is described in the first embodiment of the present invention, and will not be described herein again.
Step 2: and (4) sending the undirected weighted graph structure at the current fault moment into a K neighbor classifier to determine the fault type.
When a mechanical system fault is detected, the fault type is diagnosed immediately. And after the abnormity occurs, sending the graph structure at the current moment into a K neighbor classifier: and performing distance measurement on the tested sample and all the training samples so as to determine K adjacent samples of the tested sample. And finally, determining the category of the tested sample by using a voting method according to the category of the K adjacent sample, and determining the fault type.
The selection of the graph distance measurement directly influences the selection of the K neighbor, and further influences the classification result of the K neighbor algorithm. The true bookEmbodiments use weighted edge distances, M, for graph G and GwedThe calculation formula of (a) is as follows:
wherein Δi，jThe weighted distance between two sides of the graph model is represented by the following formula:
wherein e in the formula (8)i，jBy using
e2Only frequency information of the short-time period map is contained. When an abnormality is detected, a time t is obtainedfBy taking advantage of e2And carrying out corresponding fault diagnosis. e.g. of the typei，jAnd e'i，jThe weighted edge weights for graph G and graph G', respectively.
Fig. 5 shows a result diagram of fault identification of a bearing by using a K-nearest neighbor classification algorithm, so that the weighted edge distance between a detected signal and a training sample can be clearly seen, and the fault category of the detected sample is determined by using a voting method according to the label (fault category) of the K-nearest neighbor, so that early faults can be accurately and effectively diagnosed.
Example four
The embodiment provides a rolling bearing running state fault diagnosis system, which comprises:
(1) and the early fault detection module is used for judging that the rolling bearing has early fault by adopting the rolling bearing running state detection method according to the first embodiment.
The rolling bearing operation state detection method is described in the first embodiment of the present invention, and will not be described herein again.
(2) And the fault type identification module is used for sending the undirected weighted graph structure of the current fault moment into the K neighbor classifier and determining the fault type.
When a mechanical system fault is detected, the fault type is diagnosed immediately. And after the abnormity occurs, sending the graph structure at the current moment into a K neighbor classifier: and performing distance measurement on the tested sample and all the training samples so as to determine K adjacent samples of the tested sample. And finally, determining the category of the tested sample by using a voting method according to the category of the K adjacent sample, and determining the fault type.
The selection of the graph distance measurement directly influences the selection of the K neighbor, and further influences the classification result of the K neighbor algorithm. This embodiment uses weighted edge distances, M, for graph G and G')wedThe calculation formula of (a) is as follows:
wherein Δi，jCalculated from the following formula:
wherein e in the formula (8)i，jBy using
e2Only frequency information of the short-time period map is contained. When an abnormality is detected, a time t is obtainedfBy taking advantage of e2And carrying out corresponding fault diagnosis. e.g. of the typei，jAnd e'i，jThe weighted edge weights for graph G and graph G', respectively.
Fig. 5 shows a result diagram of fault identification of a bearing by using a K-nearest neighbor classification algorithm, so that the weighted edge distance between a detected signal and a training sample can be clearly seen, and the fault category of the detected sample is determined by using a voting method according to the label (fault category) of the K-nearest neighbor, so that early faults can be accurately and effectively diagnosed.
EXAMPLE five
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the steps in the rolling bearing operating state detection method according to the first embodiment.
EXAMPLE six
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the steps in the rolling bearing operating state fault diagnosis method according to the third embodiment.
EXAMPLE seven
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps in the rolling bearing running state detection method according to the first embodiment.
Example eight
The present embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the rolling bearing operating status failure diagnosis method according to the third embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A rolling bearing operation state detection method is characterized by comprising the following steps:
extracting a short-time period map of a vibration signal of the rolling bearing;
mapping the short-time period map by using the undirected weighted map to obtain a series of map frequencies;
and monitoring the change trend of the main spectrum frequency to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing.
2. The rolling bearing operation state detection method according to claim 1, wherein the process of extracting the short-time period map of the vibration signal of the rolling bearing is:
extracting short-time Fourier transform of a vibration signal of the rolling bearing by adopting a Hanning window;
and obtaining a discrete short-time Fourier spectrum according to the short-time Fourier transform, and calculating a corresponding short-time period map.
3. The rolling bearing operation state detection method according to claim 1, wherein the node in the undirected weighted graph is a frequency sampling point of the short-time period map.
4. The rolling bearing operation state detection method according to claim 3, wherein weighted edges in the undirected weighted graph are used to characterize correlations between nodes.
5. The rolling bearing operation state detection method according to claim 1, wherein in the process of monitoring the variation trend of the main spectrum frequency, a main spectrum frequency variation threshold value is set, and a certain control interval is set in combination with the mean value and the variance of the main spectrum frequency distribution to perform hypothesis testing to monitor the abnormality in the operation process of the rolling bearing.
6. An operating condition detection system for a rolling bearing, comprising:
the short-time period map extraction module is used for extracting a short-time period map of a vibration signal of the rolling bearing;
the map frequency mapping module is used for mapping the short-time period map by utilizing the undirected weighted map to obtain a series of map frequencies;
and the main spectrum frequency monitoring module is used for monitoring the change trend of the main spectrum frequency so as to judge the running state of the rolling bearing and realize early fault detection of the rolling bearing.
7. An operating condition fault diagnosis method for a rolling bearing, characterized by comprising:
judging that the rolling bearing has an early failure by using the rolling bearing operation state detection method according to any one of claims 1 to 5;
and (4) sending the undirected weighted graph structure at the current fault moment into a K neighbor classifier to determine the fault type.
8. The rolling bearing operating condition fault diagnosis method according to claim 7, wherein in the process of determining the fault type by the K-nearest neighbor classifier, the undirected weighted graph at the current fault moment is subjected to distance measurement with all training samples, and the distance measurement uses weighted edge distances.
9. An operational failure diagnostic system for a rolling bearing, comprising:
an early failure detection module which judges that the rolling bearing has an early failure by using the rolling bearing operation state detection method according to any one of claims 1 to 5;
and the fault type identification module is used for sending the undirected weighted graph structure of the current fault moment into the K neighbor classifier and determining the fault type.
10. A computer-readable storage medium on which a computer program is stored, characterized in that the program, when executed by a processor, implements the steps in the rolling bearing operating state detection method according to any one of claims 1 to 5;
or
The program, when executed by a processor, implements the steps in the rolling bearing operation state fault diagnosis method according to any one of claims 7 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010858165.8A CN111964909A (en) | 2020-08-24 | 2020-08-24 | Rolling bearing operation state detection method, fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010858165.8A CN111964909A (en) | 2020-08-24 | 2020-08-24 | Rolling bearing operation state detection method, fault diagnosis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111964909A true CN111964909A (en) | 2020-11-20 |
Family
ID=73389762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010858165.8A Pending CN111964909A (en) | 2020-08-24 | 2020-08-24 | Rolling bearing operation state detection method, fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111964909A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633098A (en) * | 2020-12-14 | 2021-04-09 | 华中科技大学 | Fault diagnosis method and system for rotary machine and storage medium |
| CN112687068A (en) * | 2021-03-19 | 2021-04-20 | 四川通信科研规划设计有限责任公司 | Intrusion detection method based on microwave and vibration sensor data |
| CN113280910A (en) * | 2021-04-27 | 2021-08-20 | 圣名科技(广州)有限责任公司 | Real-time monitoring method and system for long product production line equipment |
| CN113434566A (en) * | 2021-05-18 | 2021-09-24 | 广东中发星通技术有限公司 | Method and system for extracting abnormal shape features in one-dimensional time sequence detection data |
| CN114077850A (en) * | 2021-11-22 | 2022-02-22 | 西安交通大学 | Graph data-based rotating mechanical equipment state monitoring method under variable working conditions |
| CN115524002A (en) * | 2022-09-19 | 2022-12-27 | 国家电投集团河南电力有限公司 | Running state early warning method and system for power plant rotating equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102788695A (en) * | 2012-07-18 | 2012-11-21 | 南京航空航天大学 | Identification method of rolling bearing abrasion |
| JP5143194B2 (en) * | 2010-07-16 | 2013-02-13 | 中国電力株式会社 | Bearing diagnosis method |
| CN110214236A (en) * | 2017-02-24 | 2019-09-06 | Thk株式会社 | The condition diagnosing system and method for diagnosing status of rolling guide apparatus |
-
2020
- 2020-08-24 CN CN202010858165.8A patent/CN111964909A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5143194B2 (en) * | 2010-07-16 | 2013-02-13 | 中国電力株式会社 | Bearing diagnosis method |
| CN102788695A (en) * | 2012-07-18 | 2012-11-21 | 南京航空航天大学 | Identification method of rolling bearing abrasion |
| CN110214236A (en) * | 2017-02-24 | 2019-09-06 | Thk株式会社 | The condition diagnosing system and method for diagnosing status of rolling guide apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 王腾: "基于图的旋转机械健康状态评估与早期故障诊断技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633098A (en) * | 2020-12-14 | 2021-04-09 | 华中科技大学 | Fault diagnosis method and system for rotary machine and storage medium |
| CN112687068A (en) * | 2021-03-19 | 2021-04-20 | 四川通信科研规划设计有限责任公司 | Intrusion detection method based on microwave and vibration sensor data |
| CN112687068B (en) * | 2021-03-19 | 2021-05-28 | 四川通信科研规划设计有限责任公司 | Intrusion detection method based on microwave and vibration sensor data |
| CN113280910A (en) * | 2021-04-27 | 2021-08-20 | 圣名科技(广州)有限责任公司 | Real-time monitoring method and system for long product production line equipment |
| CN113434566A (en) * | 2021-05-18 | 2021-09-24 | 广东中发星通技术有限公司 | Method and system for extracting abnormal shape features in one-dimensional time sequence detection data |
| CN114077850A (en) * | 2021-11-22 | 2022-02-22 | 西安交通大学 | Graph data-based rotating mechanical equipment state monitoring method under variable working conditions |
| CN114077850B (en) * | 2021-11-22 | 2023-06-20 | 西安交通大学 | Method for monitoring state of rotary mechanical equipment based on graph data under variable working conditions |
| CN115524002A (en) * | 2022-09-19 | 2022-12-27 | 国家电投集团河南电力有限公司 | Running state early warning method and system for power plant rotating equipment and storage medium |
| CN115524002B (en) * | 2022-09-19 | 2023-08-22 | 国家电投集团河南电力有限公司 | Operation state early warning method, system and storage medium of power plant rotating equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| Shi et al. | Rolling bearing initial fault detection using long short-term memory recurrent network | |
| CN109186813B (en) | Temperature sensor self-checking device and method | |
| CN113834657B (en) | Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics | |
| US11669080B2 (en) | Abnormality detection device, abnormality detection method, and program | |
| Li et al. | Sensor fault detection with generalized likelihood ratio and correlation coefficient for bridge SHM | |
| Yan et al. | Fisher’s discriminant ratio based health indicator for locating informative frequency bands for machine performance degradation assessment | |
| Lundgren et al. | Data-driven fault diagnosis analysis and open-set classification of time-series data | |
| Delpha et al. | Kullback-Leibler Divergence for fault estimation and isolation: Application to Gamma distributed data | |
| CN108181105B (en) | Rolling bearing fault pre-diagnosis method and system based on logistic regression and J divergence | |
| CN109932179A (en) | A kind of rolling bearing fault testing method based on the reconstruct of DS Adaptive spectra | |
| CN111665066B (en) | Equipment fault self-adaptive upper and lower early warning boundary generation method based on convolutional neural network | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN111504647A (en) | AR-MSET-based performance degradation evaluation method for rolling bearing | |
| US20210149387A1 (en) | Facility failure prediction system and method for using acoustic signal of ultrasonic band | |
| CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
| CN116012681A (en) | Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion | |
| KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
| CN114739671A (en) | Bearing fault diagnosis method based on improved generalized S transformation | |
| Yan et al. | Bearing performance degradation assessment based on the continuous-scale mathematical morphological particle and feature fusion | |
| McCormick et al. | Application of periodic time-varying autoregressive models to the detection of bearing faults | |
| Jin et al. | Towards automated, integrated and unsupervised diagnosis of rolling element bearings | |
| CN111474476B (en) | Motor fault prediction method | |
| CN116627116B (en) | Process industry fault positioning method and system and electronic equipment | |
| JP2020071624A (en) | Abnormality diagnosing apparatus, abnormality diagnosing method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201120 |
|
| RJ01 | Rejection of invention patent application after publication |